{"total":100,"rows":[{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"id":"2105.05806","title":"High-Dimensional Experimental Design and Kernel Bandits","created":"2021-05-12","cited_by_count":56,"area":null},{"id":"2402.09723","title":"Efficient Prompt Optimization Through the Lens of Best Arm Identification","created":"2024-02-15","cited_by_count":37,"area":null},{"id":"2207.02575","title":"Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design","created":"2022-07-06","cited_by_count":33,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2105.13017","title":"Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits","created":"2021-05-27","cited_by_count":32,"area":null},{"id":"2302.08893","title":"Active learning for data streams: a survey","created":"2023-02-17","cited_by_count":29,"area":null},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"area":null},{"id":"2111.12151","title":"Best Arm Identification with Safety Constraints","created":"2021-11-23","cited_by_count":25,"area":null},{"id":"2210.16913","title":"Revisiting Simple Regret: Fast Rates for Returning a Good Arm","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2410.17055","title":"Optimal Design for Reward Modeling in RLHF","created":"2024-10-22","cited_by_count":25,"area":"alignment"},{"id":"2106.04763","title":"Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2021-06-09","cited_by_count":22,"area":null},{"id":"2107.09912","title":"Design of Experiments for Stochastic Contextual Linear Bandits","created":"2021-07-21","cited_by_count":18,"area":null},{"id":"2111.01768","title":"Nearly Optimal Algorithms for Level Set Estimation","created":"2021-11-02","cited_by_count":17,"area":null},{"id":"2210.15345","title":"PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits","created":"2022-10-25","cited_by_count":17,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2206.11183","title":"Active Learning with Safety Constraints","created":"2022-06-22","cited_by_count":16,"area":null},{"id":"2207.02357","title":"Instance-optimal PAC Algorithms for Contextual Bandits","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2105.06499","title":"Improved Algorithms for Agnostic Pool-based Active Classification","created":"2021-05-13","cited_by_count":15,"area":null},{"id":"2202.04294","title":"Optimal Clustering with Bandit Feedback","created":"2022-02-09","cited_by_count":15,"area":null},{"id":"2106.11612","title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","created":"2021-06-22","cited_by_count":14,"area":null},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2110.15771","title":"Collaborative Pure Exploration in Kernel Bandit","created":"2021-10-29","cited_by_count":13,"area":null},{"id":"2211.08572","title":"Bayesian Fixed-Budget Best-Arm Identification","created":"2022-11-15","cited_by_count":13,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2103.10070","title":"Top-m identification for linear bandits","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2205.13450","title":"Variance-Aware Sparse Linear Bandits","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2206.05255","title":"Interactively Learning Preference Constraints in Linear Bandits","created":"2022-06-10","cited_by_count":11,"area":null},{"id":"2306.07858","title":"Additive Causal Bandits with Unknown Graph","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2402.11156","title":"Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits","created":"2024-02-17","cited_by_count":10,"area":null},{"id":"2107.00680","title":"A Map of Bandits for E-commerce","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2207.11597","title":"Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference","created":"2022-07-23","cited_by_count":9,"area":null},{"id":"2106.14077","title":"The Role of Contextual Information in Best Arm Identification","created":"2021-06-26","cited_by_count":8,"area":null},{"id":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2110.13876","title":"Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2205.10936","title":"On Elimination Strategies for Bandit Fixed-Confidence Identification","created":"2022-05-22","cited_by_count":8,"area":null},{"id":"2102.07030","title":"Diffusion Approximations for a Class of Sequential Testing Problems","created":"2021-02-13","cited_by_count":7,"area":null},{"id":"2211.12004","title":"Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2212.09510","title":"Near-optimal Policy Identification in Active Reinforcement Learning","created":"2022-12-19","cited_by_count":7,"area":null},{"id":"2402.08406","title":"Transition Constrained Bayesian Optimization via Markov Decision Processes","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2110.14864","title":"Selective Sampling for Online Best-arm Identification","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2302.04441","title":"Multi-task Representation Learning for Pure Exploration in Linear Bandits","created":"2023-02-09","cited_by_count":6,"area":null},{"id":"2306.07549","title":"Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances","created":"2023-06-13","cited_by_count":6,"area":null},{"id":"2309.02202","title":"On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence","created":"2023-09-05","cited_by_count":6,"area":null},{"id":"2310.11015","title":"Pure Exploration in Asynchronous Federated Bandits","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2108.01152","title":"Maximizing and Satisficing in Multi-armed Bandits with Graph Information","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2306.00096","title":"Learning the Pareto Front Using Bootstrapped Observation Samples","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2311.00327","title":"Multi-task Representation Learning for Pure Exploration in Bilinear Bandits","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2412.02988","title":"Preference-based Pure Exploration","created":"2024-12-04","cited_by_count":5,"area":null},{"id":"2109.05131","title":"Near Instance Optimal Model Selection for Pure Exploration Linear Bandits","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2208.05633","title":"Best Policy Identification in Linear MDPs","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2307.11288","title":"Kernelized Offline Contextual Dueling Bandits","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2309.08709","title":"Price of Safety in Linear Best Arm Identification","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2508.16487","title":"FraPPE: Fast and Efficient Preference-based Pure Exploration","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2207.11158","title":"SPRT-based Efficient Best Arm Identification in Stochastic Bandits","created":"2022-07-22","cited_by_count":3,"area":null},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2307.15154","title":"A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2401.09073","title":"Fixed-Budget Differentially Private Best Arm Identification","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2401.17205","title":"Adaptive Experiment Design with Synthetic Controls","created":"2024-01-30","cited_by_count":2,"area":null},{"id":"2403.06230","title":"LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problem","created":"2024-03-10","cited_by_count":2,"area":null},{"id":"2410.20640","title":"Near Optimal Pure Exploration in Logistic Bandits","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2505.15643","title":"Optimal Best-Arm Identification under Fixed Confidence with Multiple Optima","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.04255","title":"Bandit Pareto Set Identification in a Multi-Output Linear Model","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2606.07931","title":"Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation","created":"2026-06-06","cited_by_count":2,"area":null},{"id":"2104.05294","title":"Pure Exploration with Structured Preference Feedback","created":"2021-04-12","cited_by_count":1,"area":"alignment"},{"id":"2206.04456","title":"Choosing Answers in $\\varepsilon$-Best-Answer Identification for Linear Bandits","created":"2022-06-09","cited_by_count":1,"area":null},{"id":"2311.00481","title":"Fixed-Budget Best-Arm Identification in Sparse Linear Bandits","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2402.13366","title":"Statistical curriculum learning: An elimination algorithm achieving an oracle risk","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2407.02601","title":"Linear Submodular Maximization with Bandit Feedback","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2506.12389","title":"Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2506.13390","title":"Experimental Design for Semiparametric Bandits","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2509.19901","title":"Pure Exploration via Frank-Wolfe Self-Play","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2605.05745","title":"Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.24803","title":"Active Learning for Stochastic Contextual Linear Bandits","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.17515","title":"Anytime-valid Optimal Policy Identification","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.06879","title":"Best-Arm Identification with Generative Proxy","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2111.04915","title":"Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers","created":"2021-11-09","cited_by_count":0,"area":null},{"id":"2302.09451","title":"Estimating Optimal Policy Value in General Linear Contextual Bandits","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2310.14751","title":"Efficient and Interpretable Bandit Algorithms","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2311.04731","title":"Robust Best-arm Identification in Linear Bandits","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2402.09467","title":"Optimal Thresholding Linear Bandit","created":"2024-02-11","cited_by_count":0,"area":null},{"id":"2501.17370","title":"Breaking the $\\log(1/\\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids","created":"2025-01-29","cited_by_count":0,"area":null},{"id":"2503.07877","title":"Cost-Aware Optimal Pairwise Pure Exploration","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2506.14479","title":"Adaptive Data Augmentation for Thompson Sampling","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2506.22480","title":"Service Placement in Small Cell Networks Using Distributed Best Arm Identification in Linear Bandits","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2602.01581","title":"Nearly Optimal Active Preference Learning and Its Application to LLM Alignment","created":"2026-02-02","cited_by_count":0,"area":"alignment"},{"id":"2603.10346","title":"On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.21180","title":"ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.03969","title":"Nearly Optimal Best Arm Identification for Semiparametric Bandits","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2605.25592","title":"Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.14706","title":"MESHA: Mechanism-Enforced Sequential Halving for Strategic Linear Bandits","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.14319","title":"Quantum Multi-Armed Bandits and Linear Bandits: Lower Bounds and Algorithms","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.22120","title":"The Price of Decentralization in Top-$K$ Arm Identification","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.13703","title":"Gap Entropy and Almost Instance-Wise Optimal Best-Arm Identification","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2610.06213","title":"Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.18577","title":"When More Objectives Make Identification Easier: The Role of Preferences and Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}